Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Support qwen2-1.5b with fused decoderlayer optimization on NPU #11888

Merged
merged 6 commits into from
Aug 22, 2024
Merged

Support qwen2-1.5b with fused decoderlayer optimization on NPU #11888

merged 6 commits into from
Aug 22, 2024

Conversation

plusbang
Copy link
Contributor

@plusbang plusbang commented Aug 21, 2024 •
edited
Loading

Description

Add qwen2-1.5B NPU support with fused decoderlayer and multi process optimization.

3. Summary of the change

  • common changes: add bias parameter for LLMBaseNNFactory.attention, fix small bug of repeat_kv
  • qwen2 specific: add related convert, add decoderrunner / prefillrunner / fuseddecoder etc, provide example script
  • llama2 specific: remove unused import

4. How to test?

@plusbang plusbang marked this pull request as ready for review August 21, 2024 10:10
@plusbang plusbang requested review from yangw1234 and sgwhat August 21, 2024 10:51
@plusbang plusbang merged commit 72a7bf6 into intel-analytics:main Aug 22, 2024
1 check passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@sgwhat sgwhat sgwhat approved these changes

@yangw1234 yangw1234 Awaiting requested review from yangw1234

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@plusbang @sgwhat